@inproceedings{3dc415d8d56f4681928b7734ebe29a2d,
title = "Form classification",
abstract = "The problem of form classification is to assign a single-page form image to one of a set of predefined form types or classes. We classify the form images using low level pixel density information from the binary images of the documents. In this paper, we solve the form classification problem with a classifier based on the k-means algorithm, supported by adaptive boosting. Our classification method is tested on the NIST scanned tax forms data bases (special forms databases 2 and 6) which include machine-typed and handwritten documents. Our method improves the performance over published results on the same databases, while still using a simple set of image features.",
keywords = "AdaBoost, Document image classification, Form classification, Image-level features, NIST tax forms datasets",
author = "Reddy, \{K. V.Umamaheswara\} and Venu Govindaraju",
year = "2008",
doi = "10.1117/12.766737",
language = "English",
isbn = "9780819469878",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
booktitle = "Document Recognition and Retrieval XV",
note = "Document Recognition and Retrieval XV ; Conference date: 29-01-2008 Through 31-01-2008",
}